most citedPre-training Vision Transformers with Formula-driven Supervised Learning

1 citations · 1 across the 1 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV20251 cited

Pre-training Vision Transformers with Formula-driven Supervised Learning

Hirokatsu Kataoka, Sora Takashima, Ryo Hayamizu +6

In the present work, we show that the performance of formula-driven supervised learning (FDSL) can match or even exceed that of ImageNet-21k and can approach that of the JFT-300M d…

cs.CV2025

Industrial Synthetic Segment Pre-training

Shinichi Mae, Ryousuke Yamada, Hirokatsu Kataoka +3

Vision Foundation Models (VFMs) have made remarkable progress and are increasingly being applied to segmentation tasks in real-world industrial settings. However, VFMs pre-trained…

cs.CV2025

Pre-training with 3D Synthetic Data: Learning 3D Point Cloud Instance Segmentation from 3D Synthetic Scenes

Daichi Otsuka, Shinichi Mae, Ryosuke Yamada +1

In the recent years, the research community has witnessed growing use of 3D point cloud data for the high applicability in various real-world applications. By means of 3D point clo…

cs.CV2025

Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding

Kohei Torimi, Ryosuke Yamada, Daichi Otsuka +4

Zero-shot recognition models require extensive training data for generalization. However, in zero-shot 3D classification, collecting 3D data and captions is costly and laborintensi…

cs.CV2024

Formula-Supervised Visual-Geometric Pre-training

Ryosuke Yamada, Kensho Hara, Hirokatsu Kataoka +4

Throughout the history of computer vision, while research has explored the integration of images (visual) and point clouds (geometric), many advancements in image and 3D object rec…

cs.CV2024

Rethinking Image Super-Resolution from Training Data Perspectives

Go Ohtani, Ryu Tadokoro, Ryosuke Yamada +7

In this work, we investigate the understudied effect of the training data used for image super-resolution (SR). Most commonly, novel SR methods are developed and benchmarked on com…